specd: Skill for Claude Code

.claude/skills/handoff/SKILL.md

handoff is a skill for Claude Code from jnerytech/specd. It costs 138 tokens per session (1,926 once invoked), scanned A, original, MIT.

A handoff workflow for recording the reasoning and unfinished work needed to continue a long task in another conversation, session, or with another agent. It includes a date, origin, and reference commit.

In plain words
What is it for?
Use it to prepare continuation context for ongoing development work and explain why decisions were made.
Why use it?
It prevents important decisions, open questions, and blockers from being lost when work moves elsewhere, without duplicating information already stored in the project.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions Claude Code.

This is jnerytech/specd's own configuration. It tells Claude Code how to work on specd itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything specd configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jnerytech/specd. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/jnerytech/specd/main/.claude/skills/handoff/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/jnerytech/specd

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for handoff

README.md
[![agentmods](https://agentmods.dev/badge/skills/jnerytech/specd/handoff/github.svg)](https://agentmods.dev/skills/jnerytech/specd/handoff)
Your own site
<a href="https://agentmods.dev/skills/jnerytech/specd/handoff"><img src="https://agentmods.dev/badge/skills/jnerytech/specd/handoff/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for handoff

Your own site · 80×15
<a href="https://agentmods.dev/skills/jnerytech/specd/handoff"><img src="https://agentmods.dev/badge/skills/jnerytech/specd/handoff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 138 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,926 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00138 $0.01926
Opus 5.5 $0.00055 $0.00770
Sonnet 5.5 $0.00028 $0.00385
Haiku 4.5 $0.00014 $0.00193

Measured 12d ago against content hash f15a5f64611c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

handoff scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/handoff/SKILL.md · 189 lines

How it starts

The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Handoff

Produz um bloco de contexto que permite retomar um trabalho longo em outro lugar, carregando o que só existe na conversa e nada além disso.

O princípio

Um handoff ruim é um resumo da conversa. Um handoff bom é o complemento do que já está durável em outro lugar.

Antes de escrever qualquer coisa, descubra o que já sobrevive sem a conversa:

  • Arquivos no repositório — decisões, princípios, documentação
  • Memória do Claude — preferências, vocabulário, regras permanentes
  • Arquivo de projeto no Claude.ai
  • Tickets, wiki, board
  • Artefatos gerados durante a conversa e já salvos

Pergunte se não souber. Duplicar o que já está versionado é pior que omitir: cria uma segunda cópia que envelhece sem ninguém perceber.

O que sobra depois desse corte é o handoff — normalmente o raciocínio, não os fatos. Por que uma decisão foi tomada, o que foi descartado e por quê, o que ainda está aberto.

O que sempre entra

Decidido, com o porquê. A decisão sozinha convida a redecidir. "Escolhemos X" é inútil; "escolhemos X porque Y falhava em Z" é o que impede a próxima sessão de voltar para Y.

Aberto, com o que trava. Questões não resolvidas e o que cada uma bloqueia. Se nada bloqueia, diga — questão aberta que não trava nada é diferente de questão aberta urgente.

Erros cometidos e corrigidos. A seção que quase todo handoff omite e a que mais evita retrabalho. Se o assistente errou e foi corrigido, isso vai junto — senão o erro volta na sessão seguinte, com a mesma confiança.

Vocabulário com significado local. Termos que a conversa passou a usar num sentido específico. Sem isso, a sessão nova usa a mesma palavra com outro sentido e ninguém percebe.

O próximo passo concreto. Não "continuar o projeto". O comando, o arquivo, a pergunta.

O que nunca entra

Contagens e estado que muda. Número de arquivos, testes, requisitos, itens concluídos. Fica errado na semana seguinte e ninguém atualiza. Aponte para o comando ou o lugar que responde.

Read the full file on GitHub · 189 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 189 lines · 138 tokens per session scan A f15a5f64611c

Subscribe to this mod's changes

handoff is a skill published in the GitHub repository jnerytech/specd (0 stars, last pushed 2mo ago), licensed MIT. It adds 138 tokens to every session and 1,926 once invoked, about $0.0006 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-02.